Skip to main content
Back to challenges
Challenge

European Heat Risk Parametric Index Monitor with OpenAI Agents SDK and Replicate

Rising chronic heat waves across Europe threaten agricultural and municipal stability, requiring automated parametric insurance payouts. You will construct an autonomous heat risk monitoring agent using the OpenAI Agents SDK and Replicate model endpoints to process Copernicus weather data. Reach an audit accuracy above 95% for automated parametric payout triggers.

Machine LearningHosted by Vera
Sign in free to start
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

Build an agent using OpenAI Agents SDK calling Replicate hosted time-series models to automate heat wave index monitoring.

Delivery guide

How work is evaluated

Evaluation

Evaluate parametric trigger execution correctness against verified weather event logs.

Datasets

Challenge datasets

Public datasets, plus the private datasets you have access to.

Evaluation rubric

How submissions are scored

These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.

Dimensions
2 scoring checks
Binary
2 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

audit_trail_exists

Agent response contains non-empty explanation of trigger conditions.

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Dimension 2

trigger_accuracy

Percentage of correct payout execution decisions • target: 0.95 • range: 0-1

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Learning goals

What you should walk away with

  • Orchestrate autonomous agent workflows using OpenAI Agents SDK

  • Integrate custom temporal forecasting models hosted on Replicate

  • Process Copernicus surface temperature time-series data

  • Implement multi-step decision logic for parametric trigger validation

Resources and assets

Reference links and supporting material

Dataset notes

European temperature time-series records combined with synthetic parametric contract definitions.

Challenge setup

Evaluate parametric trigger execution correctness against verified weather event logs.

Challenge input

JSON containing regional temperature history and policy threshold terms

OpenAI Agents SDK

Autonomous agent runtime and tool execution harness.

Replicate

Serverless host for specialised heat hazard model execution.

Evaluated output

JSON object with contract action and audit report

Evaluation checks
  • Agent response contains non-empty explanation of trigger conditions.
  • Percentage of correct payout execution decisions • target: 0.95 • range: 0-1
Configured evaluation evidence
  • Benchmark: ClimateParametricBench-2026
  • Trigger Accuracy target: 0.95
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python sandbox (unavailable on Versalist)

Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.

View technical recipe

Configured tools

Action Space
  • OpenAI · Required
  • Replicate · Optional
  • COSINE AI · Optional

Evaluation contract

  • audit_trail_exists · Weight 1
  • trigger_accuracy · Weight 1

Metrics

  • trigger_accuracy · Target 0.95

Benchmarks

  • ClimateParametricBench-2026
  • energy

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing regional temperature history and policy threshold terms

    Output: JSON object with contract action and audit report

    Execution harness: Python

Evaluation tools

  • OpenAI Agents SDK · Agent Framework
  • Replicate · Inference Infrastructure

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about European Heat Risk Parametric Index Monitor with OpenAI Agents SDK and Replicate